frandovi/vit-base-patch16-224-in21k-euroSat

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.2068
• Train Accuracy: 0.9613
• Train Top-3-accuracy: 0.9903
• Validation Loss: 0.2501
• Validation Accuracy: 0.9650
• Validation Top-3-accuracy: 0.9913
• Epoch: 4

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 665, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
1.2723	0.6941	0.8604	0.6544	0.8643	0.9573	0
0.4646	0.9004	0.9707	0.4014	0.9216	0.9784	1
0.3004	0.9348	0.9825	0.2985	0.9446	0.9855	2
0.2351	0.9514	0.9875	0.2611	0.9570	0.9892	3
0.2068	0.9613	0.9903	0.2501	0.9650	0.9913	4

Framework versions

• Transformers 4.39.1
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2